Recent advances in MEMS and information technology have enabled a new generation of sensor-rich distributed systems (e.g., smart matter systems) such as networked office document processing devices, smart buildings and structures, swarms of unmanned vehicles, and distributed self-configurable robots. At PARC, I have been investigating scalable techniques of model-based reasoning and statistical data analysis to support the modeling, diagnosis, and control of these sensor-rich embedded systems. For example, we have developed a set of time-frequency signature analysis and model-based diagnosis algorithms for monitoring health conditions of electro-mechanical machines using distributed sensors such as vibration sensors.
 

F. Zhao, X. Koutsoukos, H. Haussecker, J. Reich, P. Cheung, C. Picardi, ``Distributed Monitoring of Hybrid Systems: A model-directed approach.'' Proc. of IJCAI, August 2001. Paper (pdf).

X. Koutsoukos, F. Zhao, H. Haussecker, J. Reich, P. Cheung, Fault Modeling for Monitoring and Diagnosis of Sensor-Rich Hybrid Systems,
Proc. IEEE Conference on Decision and Control (CDC'2001), to appear, Orlando, FL, Dec. 2001.

E. Hung and F. Zhao, ``Diagnostic Information Processing for Sensor-Rich Distributed Systems.'' Proc. of 2nd International Conference on Information Fusion (Fusion'99), Sunnyvale, CA, 1999. Abstract. Paper (pdf).

S. Narasimhan, F. Zhao, G. Biswas, and E. Hung, ``Fault Isolation in Hybrid Systems Combining Model-Based Diagnosis and Signal Processing.'' Proc. of IFAC 4th Symposium on Fault Detection, Supervision, and Safety for Technical Processes.'' Budapest, 2000. Copyright 2000, IFAC. Abstract. Paper (pdf).

Back to home